Talk to your docs! This is an example agent which can be deployed to Cloudflare and your Discord server to provide help on your Github documentation.

• Discord Interactions API
• Cloudflare Workers for hosting
• bgent

Before starting, you'll need a Discord app with the following permissions:

• bot with the Send Messages and Use Slash Command permissions
• applications.commands scope

⚙️ Permissions can be configured by clicking on the OAuth2 tab and using the URL Generator. After a URL is generated, you can install the app by pasting that URL into your browser and following the installation flow.

This library uses Supabase as a database. You can set up a free account at supabase.io and create a new project.

Step 1: On the Subase All Projects Dashboard, select “New Project”.
Step 2: Select the organization to store the new project in, assign a database name, password and region.
Step 3: Select “Create New Project”.
Step 4: Wait for the database to setup. This will take a few minutes as supabase setups various directories.
Step 5: Select the “SQL Editor” tab from the left navigation menu.
Step 6: Copy in your own SQL dump file or optionally use the provided file in the bgent directory at: "https://github.com/JoinTheAlliance/bgent/blob/main/src/supabase/db.sql". Note: You can use the command "supabase db dump" if you have a pre-exisiting supabase database to generate the SQL dump file.
Step 7: Paste the SQL code into the SQL Editor and hit run in the bottom right.
Step 8: Select the “Databases” tab from the left navigation menu to verify all of the tables have been added properly.

Next, you'll need to create a Cloudflare Worker.

• Visit the Cloudflare dashboard
• Click on the Workers tab, and create a new service using the same name as your Discord bot

First clone the project:

git clone https://github.com/lalalune/afbot.git

Then navigate to its directory and install dependencies:

cd afbot
npm install

⚙️ The dependencies in this project require at least v18 of Node.js

💡 More information about generating and fetching credentials can be found in the tutorial

Rename example.dev.vars to .dev.vars, and make sure to set each variable.

.dev.vars contains sensitive data so make sure it does not get checked into git.

To refresh the commands for your bot, visit this URL in your browser:

https://localhost:8787/commands

Now you should be ready to start your server:

npm run dev

When a user types a slash command, Discord will send an HTTP request to a given endpoint. During local development this can be a little challenging, so we're going to use a tool called ngrok to create an HTTP tunnel.

npm run ngrok

This is going to bounce requests off of an external endpoint, and forward them to your machine. Copy the HTTPS link provided by the tool. It should look something like https://8098-24-22-245-250.ngrok.io. Now head back to the Discord Developer Dashboard, and update the "Interactions Endpoint URL" for your bot:

This is the process we'll use for local testing and development. When you've deployed your bot to Cloudflare, you will want to update this field to use your Cloudflare Worker URL.

This repository is set up to automatically deploy to Cloudflare Workers when new changes land on the main branch. To deploy manually, run npm run deploy, which uses the wrangler deploy command under the hood. Deploying via a GitHub Action requires obtaining an API Token and your Account ID from Cloudflare. These are stored as secrets in the GitHub repository, making them available to GitHub Actions. The following configuration in .github/workflows/ci.yaml demonstrates how to tie it all together:

release:
  if: github.ref == 'refs/heads/main'
  runs-on: ubuntu-latest
  needs: [test, lint]
  steps:
    - uses: actions/checkout@v3
    - uses: actions/setup-node@v3
      with:
        node-version: 18
    - run: npm install
    - run: npm run deploy
      env:
        CF_API_TOKEN: ${{ secrets.CF_API_TOKEN }}
        CF_ACCOUNT_ID: ${{ secrets.CF_ACCOUNT_ID }}

The credentials in .dev.vars are only applied locally. The production service needs access to credentials from your app:

wrangler secret put DISCORD_TOKEN
wrangler secret put DISCORD_PUBLIC_KEY
wrangler secret put DISCORD_APPLICATION_ID
wrangler secret put OPENAI_API_KEY
wrangler secret put SUPABASE_URL
wrangler secret put SUPABASE_SERVICE_API_KEY